This project is based on Sentiment Analysis of user reviews using Python. We are predicting the sentiment on how the user has rated the product as positive, negative, or neutral. It uses natural language processing, text analysis, computational linguistics, and biometrics to systematically identify, extract, quantify, and study affective states and subjective information. Sentiment analysis helps data analysts to understand public opinion, conduct nuanced market research, monitor brand and product reputation, and understand customer experiences. It typically involves taking a piece of text, whether it’s a sentence, a comment, or an entire document and document, and returning a ‘score’ that measures how positive or negative the text is.
This project uses the NumPy, Pandas, Matplotlib, Seaborn, Scikit Learn, Natural Language Toolkit, BeautifulSoup modules to predict the sentiment of user reviews. The algorithm used to calculate the sentiment score is Logistic Regression. Logistic regression is a supervised learning classification algorithmused to predict the probability of the target variable. The nature of the target or dependent variable is dichotomous, which means there would be only two possible classes. The project has designed in such a way that there are 2 possible classes namely sentiment and not sentimental as 1 and 0 respectively. We have also predicted the overall sentiment score where the more the sentiment score, the more is the sentiment of the text. It can also classify the user-given text as sentimental or not-sentimental as 1 or 0 respectively.